Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations include destructiveHint=true and readOnlyHint=false, but the description adds valuable behavioral disclosure: it clarifies that the tool does NOT remove or skip leads, that new leads count against quota, and that de-duplication is per workspace. It also states the agent cannot respond through the API. These details go beyond the annotation flags and set accurate expectations for side effects and limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is longer than typical but every sentence adds value—purpose, examples, differentiation, limitations, and explicit non-actions. It is front-loaded with the core action and then expands logically. While not as terse as a two-sentence ideal, it is well-organized and efficient for the complexity of the tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers the essential aspects: what the tool does, how to phrase requests, how it differs from find_leads, quota and de-duplication impacts, and what it does not do. The output schema documents the jobId return, so that is covered. No critical information for correct invocation is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so both parameters are already well-documented. The description adds marginal meaning: it clarifies that campaignId must reference an existing campaign and that message is in plain language, but these are largely redundant with the schema descriptions. The baseline of 3 applies because the schema carries the semantic load.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific action ('say something to the agent inside an EXISTING campaign') and distinguishes it from find_leads, which creates a separate campaign. It explicitly says 'Prefer this over find_leads whenever the user means more of this or not quite, adjust' and explains the consequence of using find_leads incorrectly. This leaves no ambiguity about what the tool does and when to use it.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives explicit usage conditions: use this for steering or growing a cohort, prefer it over find_leads for iterative adjustments, and provides example phrasings. It also covers limitations (quota consumption, per-workspace de-dup) and tells the agent to give instructions, not questions. This is comprehensive guidance on when and how to invoke the tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.